Copertina

A Noise Sensitivity Exponent Controls Large Statistical-to-Computational Gaps in Single- and Multi-Index Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Defilippis, Leonardo, Krzakala, Florent, Loureiro, Bruno, Maillard, Antoine
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Optimal scaling laws in learning hierarchical multi-index models
di: Defilippis, Leonardo, et al.
Pubblicazione: (2026)

Optimal Spectral Transitions in High-Dimensional Multi-Index Models
di: Defilippis, Leonardo, et al.
Pubblicazione: (2025)

Fundamental computational limits of weak learnability in high-dimensional multi-index models
di: Troiani, Emanuele, et al.
Pubblicazione: (2024)

Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks
di: Arnaboldi, Luca, et al.
Pubblicazione: (2025)

A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs
di: Tanner, Kasimir, et al.
Pubblicazione: (2024)

Online Learning and Information Exponents: On The Importance of Batch size, and Time/Complexity Tradeoffs
di: Arnaboldi, Luca, et al.
Pubblicazione: (2024)

Dimension-free deterministic equivalents and scaling laws for random feature regression
di: Defilippis, Leonardo, et al.
Pubblicazione: (2024)

Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
di: Defilippis, Leonardo, et al.
Pubblicazione: (2025)

Fundamental Limits of Matrix Sensing: Exact Asymptotics, Universality, and Applications
di: Xu, Yizhou, et al.
Pubblicazione: (2025)

Escaping mediocrity: how two-layer networks learn hard generalized linear models with SGD
di: Arnaboldi, Luca, et al.
Pubblicazione: (2023)

Computational-Statistical Gaps in Gaussian Single-Index Models
di: Damian, Alex, et al.
Pubblicazione: (2024)

High-dimensional robust regression under heavy-tailed data: Asymptotics and Universality
di: Adomaityte, Urte, et al.
Pubblicazione: (2023)

The committee machine: Computational to statistical gaps in learning a two-layers neural network
di: Aubin, Benjamin, et al.
Pubblicazione: (2018)

How Two-Layer Neural Networks Learn, One (Giant) Step at a Time
di: Dandi, Yatin, et al.
Pubblicazione: (2023)

Bayes-optimal learning of an extensive-width neural network from quadratically many samples
di: Maillard, Antoine, et al.
Pubblicazione: (2024)

Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model
di: Wortsman-Zurich, Arie, et al.
Pubblicazione: (2026)

Universality laws for Gaussian mixtures in generalized linear models
di: Dandi, Yatin, et al.
Pubblicazione: (2023)

Computational Thresholds in Multi-Modal Learning via the Spiked Matrix-Tensor Model
di: Tabanelli, Hugo, et al.
Pubblicazione: (2025)

Repetita Iuvant: Data Repetition Allows SGD to Learn High-Dimensional Multi-Index Functions
di: Arnaboldi, Luca, et al.
Pubblicazione: (2024)

The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents
di: Dandi, Yatin, et al.
Pubblicazione: (2024)

Gaussian Universality of Perceptrons with Random Labels
di: Gerace, Federica, et al.
Pubblicazione: (2022)

A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities
di: Dandi, Yatin, et al.
Pubblicazione: (2024)

The Computational Advantage of Depth: Learning High-Dimensional Hierarchical Functions with Gradient Descent
di: Dandi, Yatin, et al.
Pubblicazione: (2025)

Analysis of Bootstrap and Subsampling in High-dimensional Regularized Regression
di: Clarté, Lucas, et al.
Pubblicazione: (2024)

Provable Learning of Random Hierarchy Models and Hierarchical Shallow-to-Deep Chaining
di: Ren, Yunwei, et al.
Pubblicazione: (2026)

A phase transition between positional and semantic learning in a solvable model of dot-product attention
di: Cui, Hugo, et al.
Pubblicazione: (2024)

Asymptotics of feature learning in two-layer networks after one gradient-step
di: Cui, Hugo, et al.
Pubblicazione: (2024)

Learning with Restricted Boltzmann Machines: Asymptotics of AMP and GD in High Dimensions
di: Xu, Yizhou, et al.
Pubblicazione: (2025)

Deep Learning of Compositional Targets with Hierarchical Spectral Methods
di: Tabanelli, Hugo, et al.
Pubblicazione: (2026)

Learning Orthogonal Multi-Index Models: A Fine-Grained Information Exponent Analysis
di: Ren, Yunwei, et al.
Pubblicazione: (2024)

Fundamental limits of Non-Linear Low-Rank Matrix Estimation
di: Mergny, Pierre, et al.
Pubblicazione: (2024)

Asymptotic Characterisation of Robust Empirical Risk Minimisation Performance in the Presence of Outliers
di: Vilucchio, Matteo, et al.
Pubblicazione: (2023)

Asymptotics of Non-Convex Generalized Linear Models in High-Dimensions: A proof of the replica formula
di: Vilucchio, Matteo, et al.
Pubblicazione: (2025)

Analysis of learning a flow-based generative model from limited sample complexity
di: Cui, Hugo, et al.
Pubblicazione: (2023)

Spectral Phase Transition and Optimal PCA in Block-Structured Spiked models
di: Mergny, Pierre, et al.
Pubblicazione: (2024)

A Noise Resilient Approach for Robust Hurst Exponent Estimation
di: Premarathna, Malith, et al.
Pubblicazione: (2025)

Single-Head Attention in High Dimensions: A Theory of Generalization, Weights Spectra, and Scaling Laws
di: Boncoraglio, Fabrizio, et al.
Pubblicazione: (2025)

Sampling with flows, diffusion and autoregressive neural networks: A spin-glass perspective
di: Ghio, Davide, et al.
Pubblicazione: (2023)

The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
di: Erba, Vittorio, et al.
Pubblicazione: (2025)

Statistical-Computational Trade-offs in Learning Multi-Index Models via Harmonic Analysis
di: Latourelle-Vigeant, Hugo, et al.
Pubblicazione: (2026)